No abstract

No abstract

No abstract

No abstract

Understanding the relationship between short-term subway ridership and its influential factors is crucial to improving the accuracy of short-term subway ridership prediction. Although there has been a growing body of studies on short-term ridership prediction approaches, limited effort is made to investigate the short-term subway ridership prediction considering bus transfer activities and temporal features. To fill this gap, a relatively recent data mining approach called gradient boosting decision trees (GBDT) is applied to short-term subway ridership prediction and used to capture the associations with the independent variables. Taking three subway stations in Beijing as the cases, the short-term subway ridership and alighting passengers from its adjacent bus stops are obtained based on transit smart card data. To optimize the model performance with different combinations of regularization parameters, a series of GBDT models are built with various learning rates and tree complexities by fitting a maximum of trees. The optimal model performance confirms that the gradient boosting approach can incorporate different types of predictors, fit complex nonlinear relationships, and automatically handle the multicollinearity effect with high accuracy. In contrast to other machine learning methods-or "black-box" procedures-the GBDT model can identify and rank the relative influences of bus transfer activities and temporal features on short-term subway ridership. These findings suggest that the GBDT model has considerable advantages in improving short-term subway ridership prediction in a multimodal public transportation system.

No abstract

Fuel efficient thermal management of diesel engine aftertreatment is a significant challenge, particularly during cold start, extended idle, urban driving, and vehicle operation in cold ambient conditions. Aftertreatment systems incorporating NO xmitigating selective catalytic reduction and diesel oxidation catalysts must reach ;250°C to be effective. The primary engine-out condition that affects the ability to keep the aftertreatment components hot is the turbine outlet temperature; however, it is a combination of exhaust flow rate and turbine outlet temperature that impact the warm-up of the aftertreatment components via convective heat transfer. This article demonstrates that cylinder deactivation improves exhaust thermal management during both loaded and lightly loaded idle conditions. Coupling cylinder deactivation with flexible valve motions results in additional benefits during lightly loaded idle operation. Specifically, this article illustrates that at loaded idle, valve motion and fuel injection deactivation in three of the six cylinders enables the following: (1) a turbine outlet temperature increases from ;190°C to 310°C with only a 2% fuel economy penalty compared to the most efficient six-cylinder operation and (2) a 39% reduction in fuel consumption compared to six-cylinder operation achieving the same ;310°C turbine out temperature. Similarly, at lightly loaded idle, the combination of valve motion and fuel injection deactivation in three of the six cylinders, intake/exhaust valve throttling, and intake valve closure modulation enables the following: (1) a turbine outlet temperature increases from ;120°C to 200°C with no fuel consumption penalty compared to the most efficient six-cylinder operation and (2) turbine outlet temperatures in excess of 250°C when internal exhaust gas recirculation is also implemented. These variable valve actuation-based strategies also outperform six-cylinder operation for aftertreatment warm-up at all catalyst bed temperatures. These benefits are primarily realized by reducing the air flow through the engine, directly resulting in higher exhaust temperatures and lower pumping penalties compared to conventional six-cylinder operation. The elevated exhaust temperatures offset exhaust flow reductions, increasing exhaust gas-to-catalyst heat transfer rates, resulting in superior aftertreatment thermal management performance.

No abstract